nuclei

Object tracking. For each time-frame, an image mask is obtained from median filtering (user defined radius), thresholding (user defined level) and hole filling. Convex objects are split apart by distance map watershed from regional intensity maxima (user defined noise tolerance), eroded (user defined radius) and analyzed as 3D particles (assuming some overlap between objects from a frame to the next frame). Finally, division events are analyzed and accounted for to relabel objects.

The macro will segment nuclei and separate clustered nuclei in a 3D image using a 2D Gaussian blur, followed by Thresholding, 2D hole filling and a 2D watershed. As a result an index-mask image is written for each input image.

U-Net segmentation as presented in Reference Publication. The model predicts three classes: background, edge and foreground. The model was trained with Kaggle Data Science Bowl (DSB) 2018 training set.

Nuclei Segmentation using Deep Learning for individual cell analysis (DeepCell).